Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias | Paper Citation Record

Observation 2c596934-f23a-40f8-9017-b6ef815f24b2 · outbound

This paper cites Under- standing deep learning (still) requires rethinking generalization.Communications of the ACM, 64(3):107–115, 2021.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Under- standing deep learning (still) requires rethinking generalization.Communications of the ACM, 64(3):107–115, 2021

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1a0c1f8-4739-4246-aef6-ea1ff90c7140 · outbound

This paper cites Strogatz.Nonlinear Dynamics and Chaos: With Applications to Physics, Biology, Chemistry, and Engineering.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Strogatz.Nonlinear Dynamics and Chaos: With Applications to Physics, Biology, Chemistry, and Engineering

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 365f77c3-23c8-4e91-b5c1-12d02b0c9ab9 · outbound

This paper cites Hirsch, Stephen Smale, and Robert L.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Hirsch, Stephen Smale, and Robert L

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8dc0dd6-2ad0-4919-8139-114961bb7023 · outbound

This paper cites On the explicit role of initialization on the convergence and implicit bias of overparametrized linear networks.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias On the explicit role of initialization on the convergence and implicit bias of overparametrized linear networks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bbd45a2-25a2-4cac-9aba-619c2991b4b8 · outbound

This paper cites On the role of initialization on the implicit bias in deep linear networks, 2024.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias On the role of initialization on the implicit bias in deep linear networks, 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 311b77d0-a8c9-40bf-9851-b9eff4705123 · outbound

This paper cites Camargo, and Ard A.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Camargo, and Ard A

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55828dee-4045-40d1-b9c5-687c5e5ed24f · outbound

This paper cites an unresolved cited work.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3eae809-5fbf-48e1-ad15-e3f0cec5ed3c · outbound

This paper cites Deep-layered machines have a built-in occam’s razor.arXiv preprint arXiv:2603.01217, 2026.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Deep-layered machines have a built-in occam’s razor.arXiv preprint arXiv:2603.01217, 2026

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-06-29T13:23:28.016757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dea8f9d5-5d6e-49f7-a8c9-85716021f7f8 · outbound

This paper cites Understanding the difficulty of training deep feedforward neural networks.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Understanding the difficulty of training deep feedforward neural networks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1eb131bb-0efb-4b6f-97a1-dec28122bf92 · outbound

This paper cites Delving deep into rectifiers: Surpassing human-level performance on imagenet classification.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Delving deep into rectifiers: Surpassing human-level performance on imagenet classification

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dcdbf97-575d-424a-a620-f8d408f6edfc · outbound

This paper cites Exponential expressivity in deep neural networks through transient chaos.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Exponential expressivity in deep neural networks through transient chaos

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6052ce46-ae6c-4d81-9b06-e86ae353e396 · outbound

This paper cites Schoenholz, Justin Gilmer, Surya Ganguli, and Jascha Sohl-Dickstein.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Schoenholz, Justin Gilmer, Surya Ganguli, and Jascha Sohl-Dickstein

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e3f62e5-b038-43ab-a15e-e8af80274ee3 · outbound

This paper cites Schoenholz, and Surya Ganguli.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Schoenholz, and Surya Ganguli

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 835c2b17-2a4e-4936-8062-399c6210206d · outbound

This paper cites How to start training: The effect of initialization and architecture.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias How to start training: The effect of initialization and architecture

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fab6d43-6efe-4589-8dd9-05457b30f321 · outbound

This paper cites Which neural net architectures give rise to exploding and vanishing gradients? InAdvances in Neural Information Processing Systems, volume 31, 2018.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Which neural net architectures give rise to exploding and vanishing gradients? InAdvances in Neural Information Processing Systems, volume 31, 2018

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7031d63b-4391-429f-a54f-611d2b1f7280 · outbound

This paper cites Schoenholz, and Jeffrey Pennington.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Schoenholz, and Jeffrey Pennington

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ab31dda-82de-44fe-961f-bc675b43c1fd · outbound

This paper cites Schoenholz.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Schoenholz

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b53f382f-42ae-4071-8ead-7ed8ac60d03f · outbound

This paper cites an unresolved cited work.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87ffc089-f4cb-48e6-9e4e-ea0bc163f5d5 · outbound

This paper cites Hu, Igor Babuschkin, Szymon Sidor, Xiaodong Liu, David Farhi, Nick Ryder, Jakub Pachocki, Weizhu Chen, and Jianfeng Gao.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Hu, Igor Babuschkin, Szymon Sidor, Xiaodong Liu, David Farhi, Nick Ryder, Jakub Pachocki, Weizhu Chen, and Jianfeng Gao

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0aeb3923-10f6-4382-8109-f46aef020baf · outbound

This paper cites Self-consistent dynamical field theory of kernel evo- lution in wide neural networks.Journal of Statistical Mechanics: Theory and Experiment, 2023(11):114009, 2023.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Self-consistent dynamical field theory of kernel evo- lution in wide neural networks.Journal of Statistical Mechanics: Theory and Experiment, 2023(11):114009, 2023

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 959669ad-4ff1-42fb-8b8d-85aaaeeedace · outbound

This paper cites Dynamics of finite width kernel and prediction fluctua- tions in mean field neural networks.Journal of Statistical Mechanics: Theory and Experiment, 2024(10):104021, 2024.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Dynamics of finite width kernel and prediction fluctua- tions in mean field neural networks.Journal of Statistical Mechanics: Theory and Experiment, 2024(10):104021, 2024

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8ad1fe9-e70a-4e8e-8cc3-229c9b3a6e22 · outbound

This paper cites Deep linear network training dynamics from random initialization: Data, width, depth, and hyperparameter transfer.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Deep linear network training dynamics from random initialization: Data, width, depth, and hyperparameter transfer

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39653b32-d607-4d54-85b1-7e8f50de6c15 · outbound

This paper cites Adaptive kernel predictors from feature-learning infinite limits of neural networks.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Adaptive kernel predictors from feature-learning infinite limits of neural networks

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dce5377-20ef-4699-b079-4fc60b94cadd · outbound

This paper cites Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-06-29T13:23:28.023366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0e87974f-1ddc-4a3c-b3c4-6de0164b5687 · outbound

This paper cites Zuidema, and Stella R.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Zuidema, and Stella R

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5a575c3-3cd2-4a2f-9c56-6de3f6c0d3f6 · outbound

This paper cites Convergence and divergence of language models under different random seeds.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Convergence and divergence of language models under different random seeds

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52a8d6e3-6a7d-4bc2-9fa7-48bcabe0c4d3 · outbound

This paper cites an unresolved cited work.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed066a98-d01a-4a14-b485-c3cb3f699d19 · outbound

This paper cites SeedPrints: Fingerprints can even tell which seed your large language model was trained from.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias SeedPrints: Fingerprints can even tell which seed your large language model was trained from

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67844414-9190-4a3a-a8ba-07ad7d680aa5 · outbound

This paper cites Transformers are born biased: Structural inductive biases at random initialization and their practical consequences, 2026.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Transformers are born biased: Structural inductive biases at random initialization and their practical consequences, 2026

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c0d35fc-4e7e-4645-8698-4d51dcc1099c · outbound

This paper cites Physics of language models: Part 3.1, knowledge storage and extraction.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Physics of language models: Part 3.1, knowledge storage and extraction

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddf2782b-5f77-4546-88b9-0c8d117654e8 · outbound

This paper cites Physics of language models: Part 4.1, architecture design and the magic of canon layers.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Physics of language models: Part 4.1, architecture design and the magic of canon layers

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b544f33-ca89-4e22-9208-7ec3b063a18b · outbound

This paper cites an unresolved cited work.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 102e3f34-ffcc-47e2-b4b8-98cc50633790 · outbound

This paper cites Smith, Benoit Dherin, David G.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Smith, Benoit Dherin, David G

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 340eccbf-0333-4f24-99c4-2f019491ee60 · outbound

This paper cites On the Trajectories of SGD Without Replacement.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias On the Trajectories of SGD Without Replacement

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-06-29T13:23:28.026923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 792a5032-7557-4754-b29d-16ae3d49bc63 · outbound

This paper cites How neural networks learn the support is an implicit regularization effect of SGD.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias How neural networks learn the support is an implicit regularization effect of SGD

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb8430ce-a874-4494-8be8-19900da026c6 · outbound

This paper cites Griffiths and J.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Griffiths and J

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2a54f97-0e20-477c-b88a-c01974b367c0 · outbound

This paper cites Springer, Berlin, Heidelberg, 2 edition, 2006.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Springer, Berlin, Heidelberg, 2 edition, 2006

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2f7284f-5f07-47f3-abe4-f65a2c084bee · outbound

This paper cites Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-06-29T13:23:28.013996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 404b6453-3754-445c-a9ed-85da2b1f27b5 · outbound

This paper cites Cattaneo, Jason Matthew Klusowski, and Boris Shigida.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Cattaneo, Jason Matthew Klusowski, and Boris Shigida

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f6bdb28-49e3-4286-9b1c-4c68367e99ac · outbound

This paper cites Implicit regularization in deep matrix factorization.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Implicit regularization in deep matrix factorization

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1271a0b-d08e-4163-8536-08678091a4bd · outbound

This paper cites Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-06-29T13:23:28.020113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4ffcb543-f52f-4a7b-9281-f7295b86d721 · outbound

This paper cites an unresolved cited work.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2a3fd56-1ccb-437a-8a2c-365a15638a5f · outbound

This paper cites Vapnik and Alexey Ya.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Vapnik and Alexey Ya

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69668f97-5ebe-4014-99c9-6f4348a28622 · outbound

This paper cites Vapnik.Statistical Learning Theory.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Vapnik.Statistical Learning Theory

Reference 45

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f68f8485-8f33-4102-9bbd-db884b6210e8 · outbound

This paper cites Bartlett.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Bartlett

Reference 46

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fe5b723-7ba7-430c-9839-d8fdf7461f17 · outbound

This paper cites Bartlett and Shahar Mendelson.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Bartlett and Shahar Mendelson

Reference 47

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0731583-5306-4f76-944f-dcf59370b8cf · outbound

This paper cites Norm-based capacity control in neural networks.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Norm-based capacity control in neural networks

Reference 48

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 492ff402-a245-4242-b750-52f2f9a9a8b8 · outbound

This paper cites Bartlett, Dylan J.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Bartlett, Dylan J

Reference 49

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d872f2b2-7850-41cf-9783-6feb582a0b1f · outbound

This paper cites Understand- ing deep learning requires rethinking generalization.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Understand- ing deep learning requires rethinking generalization

Reference 50

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33cc7ff5-7afd-47d2-9d96-1f7646fdc808 · outbound

This paper cites Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, and Simon Lacoste-Julien.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, and Simon Lacoste-Julien

Reference 51

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dee2d76-6c4b-4dce-90ac-24117bc9507f · outbound

This paper cites Edelman, Fred Zhang, and Boaz Barak.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Edelman, Fred Zhang, and Boaz Barak

Reference 52

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44cf63a5-6c60-41ed-9f6a-5770a84b1bb1 · outbound

This paper cites Train faster, generalize better: Stability of stochastic gradient descent.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Train faster, generalize better: Stability of stochastic gradient descent

Reference 53

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3c3d132-634b-42fa-a6e7-99952d24d1e7 · outbound

This paper cites Exploring generalization in deep learning.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Exploring generalization in deep learning

Reference 54

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9572b56d-df5c-4b21-a23d-02476a1b3538 · outbound

This paper cites A PAC- bayesian approach to spectrally-normalized margin bounds for neural networks.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias A PAC- bayesian approach to spectrally-normalized margin bounds for neural networks

Reference 55

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54a4c63a-a5a7-401a-b00a-beea8ab6817b · outbound

This paper cites Predicting the generalization gap in deep networks with margin distributions.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Predicting the generalization gap in deep networks with margin distributions

Reference 56

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37ba5b68-355a-4ae4-bd9f-b70bdee85f91 · outbound

This paper cites Fantas- tic generalization measures and where to find them.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Fantas- tic generalization measures and where to find them

Reference 57

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 951c8d20-e516-40a7-9b88-769575bbef0a · outbound

This paper cites Flat minima.Neural Computation, 9(1):1–42, 1997.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Flat minima.Neural Computation, 9(1):1–42, 1997

Reference 58

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d44bc74-491a-48d0-9c32-a8be15a015dc · outbound

This paper cites On large-batch training for deep learning: Generalization gap and sharp minima.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias On large-batch training for deep learning: Generalization gap and sharp minima

Reference 59

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0022f79c-12d4-43af-a273-d056702d8447 · outbound

This paper cites Sharp minima can generalize for deep nets.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Sharp minima can generalize for deep nets

Reference 60

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85073a1d-1f9c-491b-b6df-b31d1c7d7a5e · outbound

This paper cites Sharpness-aware minimization for efficiently improving generalization.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Sharpness-aware minimization for efficiently improving generalization

Reference 61

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d73c9a05-c160-4b95-9a58-40fa95072139 · outbound

This paper cites McAllester.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias McAllester

Reference 62

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ad66981-77e5-4c2e-b3ba-fb0a2b4d20a9 · outbound

This paper cites an unresolved cited work.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Unresolved cited work

Reference 63

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f0f935f-3259-4953-acfd-36887d7c2c9b · outbound

This paper cites Adams, and Peter Orbanz.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Adams, and Peter Orbanz

Reference 64

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89235dd1-db05-42c0-b5b7-45fb22c95da2 · outbound

This paper cites Stronger generalization bounds for deep nets via a compression approach.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Stronger generalization bounds for deep nets via a compression approach

Reference 65

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cee32d27-e80c-4e02-8bea-71c2460319cf · outbound

This paper cites Reconciling modern machine- learning practice and the classical bias–variance trade-off.Proceedings of the National Academy of Sciences, 116(32):15849–15854, 2019.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Reconciling modern machine- learning practice and the classical bias–variance trade-off.Proceedings of the National Academy of Sciences, 116(32):15849–15854, 2019

Reference 66

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 184ac8ca-3a86-4d9f-b382-48fb077785d0 · outbound

This paper cites Deep double descent: Where bigger models and more data hurt.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Deep double descent: Where bigger models and more data hurt

Reference 67

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e5d2dc2-eb77-4bd1-8911-6f62172753d2 · outbound

This paper cites Bartlett, Philip M.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Bartlett, Philip M

Reference 68

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 293c8f82-3faa-4dc7-944b-de1130079d8a · outbound

This paper cites Neal.Bayesian Learning for Neural Networks, volume 118 ofLecture Notes in Statistics.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Neal.Bayesian Learning for Neural Networks, volume 118 ofLecture Notes in Statistics

Reference 69

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 054e625e-72b2-4a31-a638-0b3f96ba4835 · outbound

This paper cites an unresolved cited work.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Unresolved cited work

Reference 70

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e757fda-d37d-441c-919d-c95247c49b7a · outbound

This paper cites Schoenholz, Jeffrey Pennington, and Jascha Sohl-Dickstein.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Schoenholz, Jeffrey Pennington, and Jascha Sohl-Dickstein

Reference 71

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad1182f6-1d00-4f13-9cbf-0c87261f3761 · outbound

This paper cites Neural tangent kernel: Convergence and generalization in neural networks.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Neural tangent kernel: Convergence and generalization in neural networks

Reference 72

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2dc4f86-eab7-4663-84f1-cd33461828dd · outbound

This paper cites Camargo, and Ard A.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Camargo, and Ard A

Reference 73

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06d59cbf-2e4f-49ed-9b2f-d050bc648ff5 · outbound

This paper cites Random deep neural networks are biased towards simple functions.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Random deep neural networks are biased towards simple functions

Reference 74

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a58516d-7671-4d56-8fbc-b688353a4082 · outbound

This paper cites On the complexity of finite sequences.IEEE Transactions on Information Theory, 22(1):75–81, 1976.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias On the complexity of finite sequences.IEEE Transactions on Information Theory, 22(1):75–81, 1976

Reference 75

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efe22477-0dfb-41fe-9b3f-0db4bd858bc7 · outbound

This paper cites A universal algorithm for sequential data compression.IEEE Transactions on Information Theory, 23(3):337–343, 1977.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias A universal algorithm for sequential data compression.IEEE Transactions on Information Theory, 23(3):337–343, 1977

Reference 76

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c860759-7c1c-4809-8dc0-617d4b1cd3b9 · outbound

This paper cites an unresolved cited work.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Unresolved cited work

Reference 77

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f38010fe-54d6-4936-a9bd-79b9c8ad3a9d · outbound

This paper cites Simplicity bias in transformers and their ability to learn sparse Boolean functions.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Simplicity bias in transformers and their ability to learn sparse Boolean functions

Reference 78

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f55f61ac-1387-48b1-af04-c458ecbbf9e3 · outbound

This paper cites an unresolved cited work.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Unresolved cited work

Reference 79

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eece98fa-5ad6-465e-b43b-f6304f52742f · outbound

This paper cites Transformers learn low sensitivity functions: Investigations and implications.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Transformers learn low sensitivity functions: Investigations and implications

Reference 80

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0c8118a-a4b4-42af-9220-8f39358d5e53 · outbound

This paper cites Hamprecht, Yoshua Bengio, and Aaron Courville.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Hamprecht, Yoshua Bengio, and Aaron Courville

Reference 81

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0a909c4-4503-4be6-a050-86c3adab670c · outbound

This paper cites Abolafia, Jeffrey Pennington, and Jascha Sohl- Dickstein.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Abolafia, Jeffrey Pennington, and Jascha Sohl- Dickstein

Reference 82

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0816a332-0fc8-4d21-846a-11e50ef39154 · outbound

This paper cites Complexity of linear regions in deep networks.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Complexity of linear regions in deep networks

Reference 83

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35bb9b61-ad0c-4826-a601-cb840326e886 · outbound

This paper cites Deep ReLU networks have surprisingly few activation patterns.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Deep ReLU networks have surprisingly few activation patterns

Reference 84

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9526b96-f38d-4fa7-b464-81ee9d34baad · outbound

This paper cites an unresolved cited work.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Unresolved cited work

Reference 85

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02b421a0-65e6-42f6-ba40-48f47de19d0d · outbound

This paper cites Neural networks trained with SGD learn distributions of increasing complexity.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Neural networks trained with SGD learn distributions of increasing complexity

Reference 86

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a592918-713a-4b0d-a9d9-8c2306f1e8a4 · outbound

This paper cites Simplicity bias and optimization threshold in two-layer ReLU networks, 2024.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Simplicity bias and optimization threshold in two-layer ReLU networks, 2024

Reference 87

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85b5d626-2219-480c-9838-2fd867ae5a9f · outbound

This paper cites Saxe, and Peter E.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Saxe, and Peter E

Reference 88

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eebaa548-d109-42e1-b268-fc3f84ae757d · outbound

This paper cites Saxe, James L.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Saxe, James L

Reference 89

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 178408fe-3078-4103-838d-85626207a99b · outbound

This paper cites an unresolved cited work.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Unresolved cited work

Reference 90

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a5e7935-6b8e-4660-a503-11a6b3f44acf · outbound

This paper cites Tensor programs I: Wide feedforward or recurrent neural networks of any architecture are gaussian processes, 2020.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Tensor programs I: Wide feedforward or recurrent neural networks of any architecture are gaussian processes, 2020

Reference 91

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62bf712d-4e7c-4620-83e0-837fa3fe77e2 · outbound

This paper cites Batch normalization: Accelerating deep network training by reducing internal covariate shift.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Batch normalization: Accelerating deep network training by reducing internal covariate shift

Reference 92

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3568005-b996-4119-b0f9-e6f2f4ff0287 · outbound

This paper cites Theoretical analysis of auto rate-tuning by batch normalization.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Theoretical analysis of auto rate-tuning by batch normalization

Reference 93

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bba10d06-188e-404c-9db6-f7313fd141e2 · outbound

This paper cites Reconciling modern deep learning with tradi- tional optimization analyses: The intrinsic learning rate.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Reconciling modern deep learning with tradi- tional optimization analyses: The intrinsic learning rate

Reference 94

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c9bd7f4-a27b-404c-91ef-1190ab2d06c6 · outbound

This paper cites Number 32 in Notes on Applied Science.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Number 32 in Notes on Applied Science

Reference 95

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1d9de8f-c6c8-426d-809c-4cda99690ba8 · outbound

This paper cites Monographs on Numerical Analysis.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Monographs on Numerical Analysis

Reference 96

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2590ce15-2872-4ec1-a064-b1e0d5b5363e · outbound

This paper cites Higham.Accuracy and Stability of Numerical Algorithms.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Higham.Accuracy and Stability of Numerical Algorithms

Reference 97

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14ea6b90-f0b4-40f6-b3b8-5819474a3967 · outbound

This paper cites an unresolved cited work.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Unresolved cited work

Reference 98

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1cae5ec-226a-412b-9b15-affc360657b4 · outbound

This paper cites Modified equations for stochastic differential equations.BIT Numerical Mathematics, 46(1):111–125, 2006.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Modified equations for stochastic differential equations.BIT Numerical Mathematics, 46(1):111–125, 2006

Reference 99

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79a410a8-776d-4d9e-92aa-f9ab6415fbdc · outbound

This paper cites Zygalakis.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Zygalakis

Reference 100

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cac2f792-718c-4331-8a92-62d674eaa89c · outbound

This paper cites Weak backward error analysis for SDEs.SIAM Journal on Numerical Analysis, 50(3):1735–1752, 2012.

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias Weak backward error analysis for SDEs.SIAM Journal on Numerical Analysis, 50(3):1735–1752, 2012

Reference 101

Resolution: unresolved; no resolver link, observed 2026-06-29T13:20:54.303605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers